Dynamic Resource Allocation in Cloud Computing
Seyedmajid Mousavi, Amir Mosavi, Annamária R. Várkonyi-Kóczy, Gábor Fazekas · Acta Polytechnica Hungarica · 2017
Utilizing dynamic resource allocation for load balancing is considered as an important optimization process in cloud computing.In order to achieve maximum resource efficiency and scalability in a speedy manner this process is concerned with multiple objectives for an effective distribution of loads among virtual machines.In this realm, exploring new algorithms, as well as development of novel algorithms, is highly desired for technological advancement and continued progress in resource allocation application in cloud computing.Accordingly, this paper explores the application of two relatively new optimization algorithms and further proposes a hybrid algorithm for load balancing which can contribute well in maximizing the throughput of the cloud provider's network.The proposed algorithm is a hybrid of teaching-learning-based optimization algorithm (TLBO) and grey wolves optimization algorithm (GW).The hybrid algorithm performs more efficiently than utilizing every single one of these algorithms.Furthermore, it well balances the priorities and effectively considers load balancing based on time, cost, and avoidance of local optimum traps, which consequently leads to minimal amount of waiting time.To evaluate the effectiveness of the proposed algorithm, a comparison with the TLBO and GW algorithms is conducted and the experimental results are presented.Simulation tool Year Targets Environment Evolutionary algorithm Author Matlab 2014 Reduce the longest termination time among resources Reduce the resources cost Load balancing Cloud multi-target genetic Xue et al [13] GridSim 2014 Reduce the longest termination time among resources Reduce the resources cost Load balancing Grid multi-target genetic Salimi et al [14] Java environment 2012 Reduce the longest termination time among resources Load balancing Cloud genetic Cheng [15] Java environment 2013